grill-duo-with-docs

grill-duo-with-docs is a skill for Codex from murray17/rovai-ai. It costs 118 tokens per session (1,184 once invoked), scanned A, original, MIT.

A structured discussion in which a person and one fixed partner ask and answer focused questions about a plan or design, while maintaining agreed terms and authoritative decisions in documents.

In plain words
What is it for?
Clarifying a design, resolving a small set of open questions in rounds, recording confirmed vocabulary and decisions, and obtaining shared understanding before implementation.
Why use it?
It exposes unclear assumptions and keeps later decisions consistent instead of relying on scattered conversation.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Clarifying a design, resolving a small set of open questions in rounds, recording confirmed vocabulary and decisions, and obtaining shared understanding before implementation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/murray17/rovai-ai/grill-duo-with-docs
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add murray17/rovai-ai --skill grill-duo-with-docs
Clone the repo
git clone --depth 1 https://github.com/murray17/rovai-ai

Made for: Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for grill-duo-with-docs

README.md
[![agentmods](https://agentmods.dev/badge/skills/murray17/rovai-ai/grill-duo-with-docs/github.svg)](https://agentmods.dev/skills/murray17/rovai-ai/grill-duo-with-docs)
Your own site
<a href="https://agentmods.dev/skills/murray17/rovai-ai/grill-duo-with-docs"><img src="https://agentmods.dev/badge/skills/murray17/rovai-ai/grill-duo-with-docs/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for grill-duo-with-docs

Your own site · 80×15
<a href="https://agentmods.dev/skills/murray17/rovai-ai/grill-duo-with-docs"><img src="https://agentmods.dev/badge/skills/murray17/rovai-ai/grill-duo-with-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 118 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,184 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00118 $0.01184
Opus 5 $0.00059 $0.00592
Sonnet 5 $0.00024 $0.00237
Haiku 4.5 $0.00012 $0.00118

Measured 11d ago against content hash 9c8d4c3779b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

grill-duo-with-docs scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/grill-duo-with-docs/SKILL.md · 71 lines

What it actually says

双人追问与文档

邀请者负责持续追问和维护文档,一位固定搭档负责独立复核。搭档只提供建议,不修改项目文档。

角色与轮次关联

  • 用户启动会话或回答当前开放轮次:作为邀请者继续。
  • 当前 AgentRun 由文档版双人追问复核请求直接触发:作为固定搭档,只处理当前请求。
  • 当前输入是固定搭档对本轮有效邀请的直接回复:作为邀请者继续。

使用 Runtime 提供的可信发送者、当前触发消息和直接回复关系判断角色。邀请者只接受当前固定搭档对本轮有效邀请的直接回复;普通版、旧轮、失效或迟到建议只作补充,不能推进、回退或重开会话。

邀请者按需读取领域建模纪律词汇表格式决定与当前权威路由;搭档不读取这些文档规则。

基本流程

  1. 选择合格的固定搭档,每轮整理 1–4 个前提已确认、彼此不依赖的问题。
  2. 把本轮问题一次发给搭档,不附带自己的推荐。
  3. 搭档用一条消息逐题返回建议、理由和风险。
  4. 邀请者结合双方判断,一次向用户提出全部开放问题并给出推荐。
  5. 用户回答后继续当前轮,只维护已经确认的内容;当前轮全部关闭后才整理下一轮。
  6. 没有重要问题后,请用户确认共同理解;确认前不开始产品实现。

依赖本轮其它答案的问题留到下一轮。能从代码、权威文档、工具、当前输入或 Camp 公共历史查明的事实,不问用户。

固定搭档

固定搭档必须不是自己、仍在当前 Camp、能够接收请求。使用可信 Agent ID 寻址,不根据显示名或正文猜测。优先选择最匹配的成员,整场保持固定;只有用户要求、搭档离场或不可用,或者问题进入其无法有效判断的领域时才更换,并说明原因。

没有合格搭档时,明确降级为单人追问并继续相同轮次和文档规则,不虚构第二个观点。

开放轮次

一轮在所有问题被明确回答、取消或失效前保持开放,使用稳定编号 Q1Q4

  • 未回答问题保留原编号、原问题和已有搭档建议;内容未变时不重复复核。
  • 开放轮次期间不混入新问题。
  • 用户改变某题的问题、选项或约束时保留编号,只重新复核该题;此后只采用搭档对更新邀请的直接回复。
  • 用户只回答部分问题时,只维护已确认部分,并继续列出仍开放的原编号和已有建议。

消息方式

  • 邀请者请求搭档:rovai send --to <搭档 Agent ID> --body <本轮问题>
  • 搭档返回建议:rovai send --to <邀请者 Agent ID> --body <本轮建议>
  • 邀请者询问用户或请求最终确认:rovai send --to-user --body <正文>

使用可信 Agent ID。消息发送成功后结束当前响应;失败时按 CLI 返回指示处理,不盲目重发。

本轮内容

复核请求列出用户目标、已确认内容、每个问题的主要选项与约束,以及可能影响的文档。

搭档不得继续委派、增加问题或修改 CONTEXT.md、Architecture、Contract、Version Decisions 等项目文件,按原编号逐题给出建议、最主要理由和风险。

邀请者一次呈现全部开放问题,逐题说明主要取舍、自己的推荐、搭档看法和可能影响的文档;存在分歧时准确说明,并请用户按原编号回答。

维护文档

只维护用户明确确认的内容。领域词汇、当前权威、决定准入与格式、仓库规则和校验方式分别由上述三个 reference 及项目文档拥有;未回答、含糊或仅由搭档建议的内容不得写成已确认事实。

确认一项决定后,邀请者必须判断它应更新领域词汇、Architecture、Contract、当前版本 Decisions、Version 实施/验收文档中的哪几项,或者是否无需长期文档。不得创建新的数字 ADR 文件。

完成

没有重要问题后,总结已确认决定、关键约束和风险、文档变化及未确认但不阻塞的事项,并请求用户确认共同理解。用户确认后结束会话。

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 71 lines · 118 tokens per session scan A 9c8d4c3779b6

Subscribe to this mod's changes

grill-duo-with-docs is a skill published in the GitHub repository murray17/rovai-ai (64 stars, last pushed today), licensed MIT. It adds 118 tokens to every session and 1,184 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.